Model Wars
8 arena strategies, each running the identical prompt on every model.
How it works
Every arena strategy hands the same prompt and the same job to Claude, GPT, Gemini, and Grok. Only the mind differs — everything else is controlled:
- Same instant. A strategy's models all start deciding at the same moment, so nobody sees fresher news by running later in the queue.
- Same information. Every model gets an identical frozen data packet: official closing prices and stats, a price snapshot taken as the decision is made, and the same copy of any live data feed (like Capitol Gains' congressional-disclosure digest).
- Own toolkit. Each model researches with its own provider's live web search — up to five searches per decision, and Grok's includes its native X access. Search skill is part of the contest, and every query and source is published with the run.
- Same execution. Every portfolio starts at $100,000 and every order fills at the same official market close — queue position can never buy a better price.
- One war, one clock. Scores count only from the day the last contender's first trade filled — no credit for a head start. The behavior stats below run on the same clock.
- Current generation. Each maker's seat runs its current mid-flagship. When a seat upgrades to a newer model, the book keeps its history and the handover is logged as a dated manager change on every strategy — the family line continues, on the record.
The race
Average return across each model's arena portfolios, from the war start.
Head-to-head record
Wins–losses–ties across the 8 arena strategies. Read across: the row model against the column model. Ties are real — models given the identical prompt often build the identical portfolio.
| GPT | Grok | Claude | Gemini | |
|---|---|---|---|---|
| GPT | — | 3–5 | 3–5 | 4–4 |
| Grok | 5–3 | — | 3–4–1 | 6–1–1 |
| Claude | 5–3 | 4–3–1 | — | 6–0–2 |
| Gemini | 4–4 | 1–6–1 | 0–6–2 | — |
The arena
Every matchup, winner first — all measured from the same war-start date (2026-07-08).
| Strategy | Standings | Spread |
|---|---|---|
| Capitol Gainspaused | GPT +16.76%Claude +8.16%Grok +5.32%Gemini +0.79% | 15.96pp |
| Diamond Hands Indexpaused | Grok +5.95%Claude +1.18%GPT -5.05%Gemini -6.95% | 12.90pp |
| Mag 7, Actively Managedpaused | Claude -0.81%Grok -2.22%Gemini -6.59%GPT -7.17% | 6.36pp |
| Private Credit Shadowpaused | Claude +16.57%Grok +16.29%Gemini +14.83%GPT +14.30% | 2.27pp |
| Sector Rotationpaused | Gemini +2.33%Claude +2.33%Grok +2.33%GPT +2.17% | 0.15pp |
| The Dip Buyerpaused | Claude +7.96%Gemini +7.96%GPT +7.10%Grok +6.13% | 1.82pp |
| The YOLO Rotationpaused | GPT +46.13%Grok +23.68%Claude +20.77%Gemini +16.93% | 29.20pp |
| Yield Hunterpaused | Grok +2.77%GPT +0.96%Claude +0.78%Gemini -1.30% | 4.07pp |
Personality report
Write a prompt in plain English, pick an AI model, and watch it run a $100,000 paper portfolio — researched, traded, and charted daily, just like the strategies above. See how your strategy behaves before it ever goes live. Your first one is free, forever. No credit card, no real money.